# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\w+)(?:(?:@)|(?:\s+[Aa][Tt]\s+))(.+)(?:(?:\.edu)|(?:\s+[dD][oO][Tt]\s+edu))"
test_str = ("ashishg e ashishg@stanford.edu\n"
"ashishg e rozm@stanford.edu\n"
"ashishg p 650-723-1614\n"
"ashishg p 650-723-4173\n"
"ashishg p 650-814-1478\n"
"balaji e balaji@stanford.edu\n"
"bgirod p 650-723-4539\n"
"bgirod p 650-724-3648\n"
"bgirod p 650-724-6354\n"
"cheriton e cheriton@cs.stanford.edu\n"
"cheriton e uma@cs.stanford.edu\n"
"cheriton p 650-723-1131\n"
"cheriton p 650-725-3726\n"
"dabo e dabo@cs.stanford.edu\n"
"dabo p 650-725-3897\n"
"dabo p 650-725-4671\n"
"dlwh e dlwh@stanford.edu\n"
"engler e engler@lcs.mit.edu\n"
"engler e engler@stanford.edu\n"
"eroberts e eroberts@cs.stanford.edu\n"
"eroberts p 650-723-3642\n"
"eroberts p 650-723-6092\n"
"fedkiw e fedkiw@cs.stanford.edu\n"
"hager e hager@cs.jhu.edu\n"
"hager p 410-516-5521\n"
"hager p 410-516-5553\n"
"hager p 410-516-8000\n"
"hanrahan e hanrahan@cs.stanford.edu\n"
"hanrahan p 650-723-0033\n"
"hanrahan p 650-723-8530\n"
"horowitz p 650-725-3707\n"
"horowitz p 650-725-6949\n"
"jks e jks@robotics.stanford.edu\n"
"jurafsky e jurafsky@stanford.edu\n"
"jurafsky p 650-723-5666\n"
"kosecka e kosecka@cs.gmu.edu\n"
"kosecka p 703-993-1710\n"
"kosecka p 703-993-1876\n"
"kunle e darlene@csl.stanford.edu\n"
"kunle e kunle@ogun.stanford.edu\n"
"kunle p 650-723-1430\n"
"kunle p 650-725-3713\n"
"kunle p 650-725-6949\n"
"lam e lam@cs.stanford.edu\n"
"lam p 650-725-3714\n"
"lam p 650-725-6949\n"
"latombe e asandra@cs.stanford.edu\n"
"latombe e latombe@cs.stanford.edu\n"
"latombe e liliana@cs.stanford.edu\n"
"latombe p 650-721-6625\n"
"latombe p 650-723-0350\n"
"latombe p 650-723-4137\n"
"latombe p 650-725-1449\n"
"levoy e ada@graphics.stanford.edu\n"
"levoy e melissa@graphics.stanford.edu\n"
"levoy p 650-723-0033\n"
"levoy p 650-724-6865\n"
"levoy p 650-725-3724\n"
"levoy p 650-725-4089\n"
"manning e dbarros@cs.stanford.edu\n"
"manning e manning@cs.stanford.edu\n"
"manning p 650-723-7683\n"
"manning p 650-725-1449\n"
"manning p 650-725-3358\n"
"nass e nass@stanford.edu\n"
"nass p 650-723-5499\n"
"nass p 650-725-2472\n"
"nick e nick.parlante@cs.stanford.edu\n"
"nick p 650-725-4727\n"
"ok p 650-723-9753\n"
"ok p 650-725-1449\n"
"ouster e teresa.lynn@stanford.edu\n"
"ouster e ouster@cs.stanford.edu\n"
"pal e pal@cs.stanford.edu\n"
"pal p 650-725-9046\n"
"psyoung e patrick.young@stanford.edu\n"
"rajeev p 650-723-4377\n"
"rajeev p 650-723-6045\n"
"rajeev p 650-725-4671\n"
"rinard e rinard@lcs.mit.edu\n"
"rinard p 617-253-1221\n"
"rinard p 617-258-6922\n"
"serafim e serafim@cs.stanford.edu\n"
"serafim p 650-723-3334\n"
"serafim p 650-725-1449\n"
"shoham e shoham@stanford.edu\n"
"shoham p 650-723-3432\n"
"shoham p 650-725-1449\n"
"subh e subh@stanford.edu\n"
"subh e uma@cs.stanford.edu\n"
"subh p 650-724-1915\n"
"subh p 650-725-3726\n"
"subh p 650-725-6949\n"
"thm e pkrokel@stanford.edu\n"
"thm p 650-725-3383\n"
"thm p 650-725-3636\n"
"thm p 650-725-3938\n"
"tim p 650-724-9147\n"
"tim p 650-725-2340\n"
"tim p 650-725-4671\n"
"ullman e support@gradiance.com\n"
"ullman e ullman@cs.stanford.edu\n"
"ullman p 650-494-8016\n"
"ullman p 650-725-2588\n"
"ullman p 650-725-4802\n"
"vladlen e vladlen@stanford.edu\n"
"widom e siroker@cs.stanford.edu\n"
"widom e widom@cs.stanford.edu\n"
"widom p 650-723-0872\n"
"widom p 650-723-7690\n"
"widom p 650-725-2588\n"
"zelenski e zelenski@cs.stanford.edu\n"
"zelenski p 650-723-6092\n"
"zelenski p 650-725-8596\n"
"zm e manna@cs.stanford.edu\n"
"zm p 650-723-4364\n"
"zm p 650-725-4671\n"
"650-725-4671\n"
"650-725-4671\n"
"6103564533\n"
"(610)3564533\n"
"(610) 356-4533 \n"
"610.405.0420\n"
"6104050420\n"
"16104050420\n"
"610.405-0420\n"
"610.405-0420\n\n\n\n\n")
matches = re.finditer(regex, test_str)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html